苏卓

教师简介: 

苏卓 博士，bat365在线中国登录入口副教授，博士生导师，国家数字家庭工程技术研究中心研究员。2014年6月博士毕业于bat365官方网站登录计算机系，2012-2013年于香港中文大学计算机科学与工程系从事研究工作。已在IEEE Trans. on Image Processing (TIP)/Multimedia (TMM)/Circuits and Systems for Video Technology (TCSVT)，ACM Trans. on Multi. Comm. Appl. (TOMM)，Neucomputing，ACM Multimedia，IJCAI，ICME，计算机辅助设计与图形学学报等国内外知名学术期刊和会议上发表学术论文四十多篇。主持国家自然科学基金面上项目和青年科学基金项目、广东省重点研发计划课题，广东省自然科学基金项目、bat365官方网站登录青年教师培育项目，并参与多项国家及省市科研项目。获2022年度教育部高等学校优秀成果科技进步二等奖，2015年度ACM优秀博士论文奖(广州)，2012年度教育部博士研究生学术新人奖等奖项。

招收：欢迎计算机科学与技术、软件工程、信息与计算科学等相关专业的同学报考本人的研究生（含学硕(计算机科学与技术)、专硕(计算机技术、软件工程)），以及各年级优秀本科同学加入实验室。

研究领域: 

智能视觉计算理论与应用，以人为中心的视觉理解技术，通用多模态AI计算系统及关键技术

教育背景: 

• 2004.09--2014.06，bat365官方网站登录，工学学士，工程硕士，工学博士
• 2012.09--2013.08，香港中文大学，计算机科学与工程系，学术RA

工作经历: 

• 2019.01至今，bat365官方网站登录，bat365在线中国登录入口，副教授，博导/硕导
• 2014.06至今，bat365官方网站登录国家数字家庭工程技术研究中心，研究员
• 2014.12--2018.12，bat365官方网站登录，数据科学与bat365在线中国登录入口，讲师

教授课程: 

• 数据结构与算法（本科生课程）
• 计算机图形学（本科生课程）
• 计算可视媒体（全日制研究生课程）
• 数字图像处理（非全日制研究生课程）
• 科技论文写作（全日制研究生课程）

代表性论著: 

2024

• [1] Z. Su, L. Zhou, Y. Tan, B. Guan, F. Zhou, Weakly Supervised Point Cloud Segmentation Using Visual Boundary Prior-Driven Pseudo-Labeling for 3D Indoor Scenes, IEEE Transactions on Visualization and Computer Graphics, Early Access, 2024 (JCR Q1, CCF-A Journal)

• [2] Y. Feng, L. Ma, X. Meng, F. Zhou, R. Liu, Z. Su*, Advancing Real-World Image Dehazing: Perspective, Modules, and Training, IEEE Transactions on Pattern Analysis and Machine Intelligence, Early Access, 2024 (JCR Q1, CCF-A Journal)

• [3] S. Zhou, F. Zhang, R. Wang, F. Zhou, Z. Su*, Subtask Prior-driven Optimized Mechanism on Joint Video Moment Retrieval and Highlight Detection, IEEE Transactions on Circuits and Systems for Video Technology, Early Access, 2024 (JCR Q1, CCF-B Journal)

• [4] Y. Feng, Z. Su, L. Ma, X. Li, R. Liu, F. Zhou, Bridging the Gap Between Haze Scenarios: A Unified Image Dehazing Model​, IEEE Transactions on Circuits and Systems for Video Technology, Early Access, 2024 (JCR Q1, CCF-B Journal)

• [5] X. Li, Y. Feng, F. Zhou, Y. Liang, Z. Su*, Revitalizing Real Image Deraining via a Generic Paradigm towards Multiple Rainy Patterns, IJCAI 2024, 1029-1037 (CCF-A Conference)

• [6] Z. Su, Y. Chen, F. Zhang, F. Zhou, R. Wang, G. Lin, DMAP: Decoupling-driven Multi-level Attribute Parsing for Interpretable Outfit Collocation, IEEE Transactions on Multimedia, 26, 9988-10000, 2024 (JCR Q1, CCF-B Journal)

2023

• [1] Y. Feng, X. Meng, F. Zhou, W. Lin, Z. Su*, Real-world non-homogeneous haze removal by sliding self-attention wavelet network, IEEE Transactions on Circuits and Systems for Video Technology, 33(10), 5460-5485, 2023 (JCR Q1, CCF-B Journal)

• [2] Y. Tan, B. Guan, F. Zhou, Z. Su*, OaIF: Occlusion-aware implicit function for clothed human re-construction, Computer Graphics Forum, 42(6), e14798, 2023 (CCF-B Journal)

• [3] Z. Su, H. Guan, Y. Lai, F. Zhou, Y. Liang, Boundary-guided part reasoning network for human parsing, Neurocomputing, 561, 126876, 2023 (CCF-C Journal)

• [4] J. Pu, L. Liu, X. Fu, Z. Su, L. Liu, W. Peng, Feature representation for high-resolution clothed human reconstruction, Computer Graphics Forum, 42(6), e14792, 2023 (CCF-B Journal)

• [5] Z. Su, R. Liu, Y. Feng, F. Zhou, Attention-adaptive multi-scale feature aggregation dehazing network, Journal of Visual Communication and Image Representation, 90, 103706, 2023 (CCF-C Journal) 

• [6] X. Meng, R. Liu, Z. Su*, F. Zhou, Transfer learning dehazing network by Gaussian process mapping, Signal Processing: Image Communication, 119, 117033, 2023 (CCF-C Journal) 

• [7] X. Meng, Y. Feng, F. Zhou, Y. Liang, Z. Su*, Towards real-world haze removal with uncorrelated graph model, Journal of Visual Communication and Image Representation, 96, 103927, 2023 (CCF-C Journal)

2022

• [1] Y. Liang, E. Huang, Z. Zhang, Z. Su*, D. Wang, Feature dense relevance network for single image dehazing, Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI), 1144-1150, 2022 (CCF-A Conference)

• [2] X. Meng, Y. Feng, Z. Su*, F. Zhou, Unsupervised domain adaptation image dehazing with contrastive nearest-farthest subspace distance, IEEE International Conference on Multimedia and Expo (ICME), 1-6, 2022 (CCF-B Conference)

• [3] C. Liu, R. Liu, Z. Su*, F. Zhou, Multi-target domain transfer detector on bad weather conditions, IEEE International Conference on Multimedia and Expo (ICME), 1-6, 2022 (CCF-B Conference)

• [4] Z. Zhou, Z. Su*, R. Wang, Attribute-aware heterogeneous graph network for fashion compatibility prediction, Neurocomputing, 495, 62-74, 2022 (CCF-C Journal)

• [5] S. Liang, X. Meng, Z. Su*, F. Zhou, Multi-receptive field aggregation network for single image deraining, Journal of Visual Communication and Image Representation, 84 , 103469, 2022 (CCF-C Journal)

2021 & BEFORE

• [1] Z. Su*, M. Chen, E. Huang, G. Lin, F. Zhou, MVSN: A multi-view stack network for human parsing, Neurocomputing, 465, 437-450, 2021 (CCF-C Journal)

• [2] E. Huang, Z. Su*, F. Zhou, R. Wang, Learning rebalanced human parsing model from imbalanced datasets, Image and Vision Computing, 99, 103928, 2020 (CCF-C Journal)

• [3] E. Huang , Z. Su, F. Zhou, Tao: A trilateral awareness operation for human parsing, IEEE International Conference on Multimedia and Expo (ICME), 1-6, 2020 (CCF-B Conference)

• [4] X. Liang, B. Qiu, Z. Su*, C. Gao, X. Shi, R. Wang, Rain wiper: An incremental randomly wired network for single image deraining, Computer Graphics Forum, 38(7), 2019 (CCF-B Journal)

• [5] X. Luo, Z. Su*, J. Guo, G. Zhang, X. He, Trusted guidance pyramid network for human parsing, ACM Multimedia, 654-662, 2018 (CCF-A Conference)

• [6] Y. Cai, Q. Liu, C. Gao, Z. Su, FashionGAN: Display your fashion design using conditional generative adversarial nets, Computer Graphics Forum, 37(7), 2018 (CCF-B Journal)

• [7] B. Li, F. Zhao, Z. Su, X. Liang, Y. Lai, P. Rosin, Example-based image colorization using locality consistent sparse representation, IEEE Transactions on Image Process, 26(11): 5188-5202, 2017  (JCR Q1, CCF-A Journal)

• [8] Z. Su, K. Zeng, H. Li, X. Luo, A dual-domain perceptual framework for generating visual inconspicuous counterparts, ACM Trans. Multim. Comput. Commun. Appl., 13(2): 22:1-22:21, 2017 (CCF-B Journal)

• [9] Z. Su, K. Zeng, L. Liu, B. Li, X. Luo, Corruptive artifacts suppression for example-based color transfer, IEEE Transactions on Multimedia, 16(4): 988-999, 2014 (JCR Q1, CCF-B Journal)

• [10] Z. Su, X. Luo, Z. Deng, Y. Liang, Z. Ji, Edge-preserving texture suppression filter based on joint filtering schemes, IEEE Transactions on Multimedia, 15(3): 535-548, 2013 (JCR Q1, CCF-B Journal)

• * Note: More work please see my personal academic homepage in Github.